Add bibtex support to load_data() (#1190)

* Add support for loading Bibtex data.

* Add load_data() documentation for the bibtex format

* Force bibtex tags to be lower case.

Bibtex tags are case-insensitive, and this works around tera's case-sensitiveness.

* Improve the load_data() documentation for the bibtex format

Cargo.lock

@@ -51,6 +51,12 @@ dependencies = [
  "winapi 0.3.9",
 ]
 
+[[package]]
+name = "arrayvec"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cff77d8686867eceff3105329d4698d96c2391c176d5d03adc90c7389162b5b8"
+
 [[package]]
 name = "assert-json-diff"
 version = "1.1.0"
@@ -161,6 +167,18 @@ version = "0.3.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3b5ca7a04898ad4bcd41c90c5285445ff5b791899bb1b0abdd2a2aa791211d7"
 
+[[package]]
+name = "bytecount"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f861d9ce359f56dbcb6e0c2a1cb84e52ad732cadb57b806adeb3c7668caccbd8"
+
+[[package]]
+name = "bytecount"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b0017894339f586ccb943b01b9555de56770c11cda818e7e3d8bd93f4ed7f46e"
+
 [[package]]
 name = "bytemuck"
 version = "1.4.1"
@@ -1158,6 +1176,19 @@ version = "0.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "73a004f877f468548d8d0ac4977456a249d8fabbdb8416c36db163dfc8f2e8ca"
 
+[[package]]
+name = "lexical-core"
+version = "0.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db65c6da02e61f55dae90a0ae427b2a5f6b3e8db09f58d10efab23af92592616"
+dependencies = [
+ "arrayvec",
+ "bitflags",
+ "cfg-if",
+ "ryu",
+ "static_assertions",
+]
+
 [[package]]
 name = "libc"
 version = "0.2.80"
@@ -1483,6 +1514,73 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "nom"
+version = "5.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ffb4262d26ed83a1c0a33a38fe2bb15797329c85770da05e6b828ddb782627af"
+dependencies = [
+ "lexical-core",
+ "memchr",
+ "version_check",
+]
+
+[[package]]
+name = "nom-bibtex"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c9db257f6c7b9c8b3ab67ee6a4b23a290c157d183fef2ac065bf9fce5f1c1299"
+dependencies = [
+ "nom",
+ "nom-tracable",
+ "nom_locate 2.0.0",
+ "quick-error",
+]
+
+[[package]]
+name = "nom-tracable"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e012c742e1269f801f6bfe0d1ebf99d7a3f7bc1d65c970bab0e7bee439e31610"
+dependencies = [
+ "nom",
+ "nom-tracable-macros",
+ "nom_locate 1.0.0",
+ "nom_locate 2.0.0",
+]
+
+[[package]]
+name = "nom-tracable-macros"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65ad630ff46d4c61da89042f327e6fdf104a6ebb667565727ef0bb294a7c3197"
+dependencies = [
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "nom_locate"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f932834fd8e391fc7710e2ba17e8f9f8645d846b55aa63207e17e110a1e1ce35"
+dependencies = [
+ "bytecount 0.3.2",
+ "memchr",
+ "nom",
+]
+
+[[package]]
+name = "nom_locate"
+version = "2.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1e4726500a3d0297dd38edc169d919ad997a9931b4645b59ce0231e88536e213"
+dependencies = [
+ "bytecount 0.6.0",
+ "memchr",
+ "nom",
+]
+
 [[package]]
 name = "notify"
 version = "4.0.15"
@@ -1849,6 +1947,12 @@ dependencies = [
  "unicase",
 ]
 
+[[package]]
+name = "quick-error"
+version = "1.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
+
 [[package]]
 name = "quote"
 version = "1.0.7"
@@ -2317,6 +2421,12 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "6e63cff320ae2c57904679ba7cb63280a3dc4613885beafb148ee7bf9aa9042d"
 
+[[package]]
+name = "static_assertions"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f"
+
 [[package]]
 name = "string_cache"
 version = "0.8.0"
@@ -2438,6 +2548,7 @@ dependencies = [
  "lazy_static",
  "library",
  "mockito",
+ "nom-bibtex",
  "pulldown-cmark",
  "reqwest",
  "serde_json",

components/templates/Cargo.toml

@@ -15,6 +15,7 @@ image = "0.23"
 serde_json = "1.0"
 sha2 = "0.9"
 url = "2"
+nom-bibtex = "0.3"
 
 errors = { path = "../errors" }
 utils = { path = "../utils" }

components/templates/src/global_fns/load_data.rs

@@ -28,6 +28,7 @@ enum OutputFormat {
     Toml,
     Json,
     Csv,
+    Bibtex,
     Plain,
 }
 
@@ -51,6 +52,7 @@ impl FromStr for OutputFormat {
             "toml" => Ok(OutputFormat::Toml),
             "csv" => Ok(OutputFormat::Csv),
             "json" => Ok(OutputFormat::Json),
+            "bibtex" => Ok(OutputFormat::Bibtex),
             "plain" => Ok(OutputFormat::Plain),
             format => Err(format!("Unknown output format {}", format).into()),
         }
@@ -63,6 +65,7 @@ impl OutputFormat {
             OutputFormat::Json => "application/json",
             OutputFormat::Csv => "text/csv",
             OutputFormat::Toml => "application/toml",
+            OutputFormat::Bibtex => "application/x-bibtex",
             OutputFormat::Plain => "text/plain",
         })
     }
@@ -148,7 +151,7 @@ fn get_output_format_from_args(
     let format_arg = optional_arg!(
         String,
         args.get("format"),
-        "`load_data`: `format` needs to be an argument with a string value, being one of the supported `load_data` file types (csv, json, toml, plain)"
+        "`load_data`: `format` needs to be an argument with a string value, being one of the supported `load_data` file types (csv, json, toml, bibtex, plain)"
     );
 
     if let Some(format) = format_arg {
@@ -169,7 +172,7 @@ fn get_output_format_from_args(
 }
 
 /// A Tera function to load data from a file or from a URL
-/// Currently the supported formats are json, toml, csv and plain text
+/// Currently the supported formats are json, toml, csv, bibtex and plain text
 #[derive(Debug)]
 pub struct LoadData {
     base_path: PathBuf,
@@ -223,6 +226,7 @@ impl TeraFn for LoadData {
             OutputFormat::Toml => load_toml(data),
             OutputFormat::Csv => load_csv(data),
             OutputFormat::Json => load_json(data),
+            OutputFormat::Bibtex => load_bibtex(data),
             OutputFormat::Plain => to_value(data).map_err(|e| e.into()),
         };
 
@@ -252,6 +256,51 @@ fn load_toml(toml_data: String) -> Result<Value> {
     }
 }
 
+/// Parse a BIBTEX string and convert it to a Tera Value
+fn load_bibtex(bibtex_data: String) -> Result<Value> {
+    let bibtex_model = nom_bibtex::Bibtex::parse(&bibtex_data).map_err(|e| format!("{:?}", e))?;
+    let mut bibtex_map = Map::new();
+
+    let preambles_array = bibtex_model.preambles()
+        .iter()
+        .map(|v| Value::String(v.to_string()))
+        .collect();
+    bibtex_map.insert(String::from("preambles"), Value::Array(preambles_array));
+
+    let comments_array = bibtex_model.comments()
+        .iter()
+        .map(|v| Value::String(v.to_string()))
+        .collect();
+    bibtex_map.insert(String::from("comments"), Value::Array(comments_array));
+
+    let mut variables_map = Map::new();
+    for (key,val) in bibtex_model.variables() {
+        variables_map.insert(key.to_string(), Value::String(val.to_string()));
+    }
+    bibtex_map.insert(String::from("variables"), Value::Object(variables_map));
+
+    let bibliographies_array = bibtex_model.bibliographies()
+        .iter()
+        .map(|b| {
+            let mut m = Map::new();
+            m.insert(String::from("entry_type"), Value::String(b.entry_type().to_string()));
+            m.insert(String::from("citation_key"), Value::String(b.citation_key().to_string()));
+
+            let mut tags = Map::new();
+            for (key, val) in b.tags() {
+                tags.insert(key.to_lowercase().to_string(), Value::String(val.to_string()));
+            }
+            m.insert(String::from("tags"), Value::Object(tags));
+            Value::Object(m)
+        })
+        .collect();
+    bibtex_map.insert(String::from("bibliographies"), Value::Array(bibliographies_array));
+
+    let bibtex_value: Value = Value::Object(bibtex_map);
+    to_value(bibtex_value).map_err(|err| err.into())
+}
+
+
 /// Parse a CSV string and convert it to a Tera Value
 ///
 /// An example csv file `example.csv` could be:

docs/content/documentation/templates/overview.md

@@ -202,7 +202,7 @@ items: Array<TaxonomyTerm>;
 See the [Taxonomies documentation](@/documentation/templates/taxonomies.md) for a full documentation of those types.
 
 ### `load_data`
-Loads data from a file or URL. Supported file types include *toml*, *json* and *csv*.
+Loads data from a file or URL. Supported file types include *toml*, *json*, *csv* and *bibtex*.
 Any other file type will be loaded as plain text.
 
 The `path` argument specifies the path to the data file relative to your base directory, where your `config.toml` is.
@@ -213,7 +213,7 @@ As a security precaution, if this file is outside the main site directory, your
 ```
 
 The optional `format` argument allows you to specify and override which data type is contained
-within the file specified in the `path` argument. Valid entries are `toml`, `json`, `csv`
+within the file specified in the `path` argument. Valid entries are `toml`, `json`, `csv`, `bibtex`
 or `plain`. If the `format` argument isn't specified, then the path extension is used.
 
 ```jinja2
@@ -251,6 +251,58 @@ template:
 }
 ```
 
+The `bibtex` format loads data into a structure matching the format used by the
+[nom-bibtex crate](https://crates.io/crates/nom-bibtex). The following is an example of data
+in bibtex format:
+
+```
+@preamble{"A bibtex preamble" # " this is."}
+
+@Comment{
+    Here is a comment.
+}
+
+Another comment!
+
+@string(name = "Vincent Prouillet")
+@string(github = "https://github.com/getzola/zola")
+
+@misc {my_citation_key,
+    author= name,
+    title = "Zola",
+    note = "github: " # github
+}                                                    }
+```
+
+The following is the json-equivalent format of the produced bibtex data structure:
+```json
+{
+    "preambles": ["A bibtex preamble this is."],
+    "comments": ["Here is a comment.", "Another comment!"],
+    "variables": {
+        "name": "Vincent Prouillet",
+        "github": "https://github.com/getzola/zola"
+    },
+    "bibliographies": [
+        {
+            "entry_type": "misc",
+            "citation_key": "my_citation_key",
+            "tags": {
+                "author": "Vincent Prouillet",
+                "title": "Zola",
+                "note": "github: https://github.com/getzola/zola"
+            }
+        }
+    ]
+}
+```
+
+Finally, the bibtex data can be accessed from the template as follows:
+```jinja2
+{% set tags = data.bibliographies[0].tags %}
+This was generated using {{ tags.title }}, authored by {{ tags.author }}.
+```
+
 #### Remote content
 
 Instead of using a file, you can load data from a remote URL. This can be done by specifying a `url` parameter